System and method for providing a natural language interface to a database

• US 7,921,091 B2
• Filed: 12/16/2004
• Issued: 04/05/2011
• Est. Priority Date: 12/16/2004
• Status: Active Grant

• Current Assignee: Bampton Technologies, LLC (Intellectual Ventures LLC)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Cox, Richard Vandervoort, Nadji, Behzad, Eslambolchi, Hossein, Rahim, Mazin G.
• Primary Examiner(s): Fleurantin; Jean B.
• Assistant Examiner(s): Jami; Hares
• Application Number:
  US11/013,836
• Publication Number:
  US 20060136375A1
• Time in Patent Office: 2,301 Days
• Field of Search: 707 1- 3, 707/705, 707/706, 707/758, 707/736, 707/769, 704/9
• US Class Current: 707/705
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence

Abstract

A system and method for providing a natural language interface to a database or the Internet. The method provides a response from a database to a natural language query. The method comprises receiving a user query, extracting key data from the user query, submitting the extracted key data to a data base search engine to retrieve a top n pages from the data base, processing of the top n pages through a natural language dialog engine and providing a response based on processing the top n pages.

Claims

1. A method for providing a response to a user query, the method performed at least in part via a processor, the method comprising:

receiving the user query;

extracting key data from the user query;

submitting the key data to a database search engine to execute a search to retrieve a top n pages from the database, wherein “

n”

is an integer;

preprocessing pages in the top n pages if a restriction exists to access the top n pages, by negotiating the restriction by automatically providing user login and password information, overcome the restriction;

prior to responding to the user query, processing the top n pages through a natural language dialog engine to generate text for the response;

providing the response comprising an audible response and a text-based response based on the text from processing the top n pages, wherein the response includes a link to more information related to the response;

after providing the response and without further user input, automatically expanding the search based on the user query by continuing to find related information using a machine learning process; and

forwarding, for display to the user, an option to view the related information separate from the provided response.

2. The method of claim 1, wherein the user query is one of a natural language speech query or a text based query.

3. The method of claim 1, wherein the key data is at least one of the key words and key phrases.

4. The method of claim 1, wherein submitting at the key data to the database search engine further comprises submitting at the key data to a plurality of search engines.

5. The method of claim 1, wherein the user can select one of:

a text input mode, a speech input mode or a dialog mode.

6. The method of claim 1, wherein the user input is received via a large vocabulary speech recognizer.

7. The method of claim 1 wherein the response is a natural language response provided via synthetic speech.

8. The method of claim 1, wherein the response is a multimedia response.

9. The method of claim 1, wherein the database is one of:

the World Wide Web, a multimedia data base, a corporate data base or personal data base.

10. The method of claim 1, wherein the user query and response are provided in a dialog mode.

11. The method of claim 1, wherein the user interacts with a virtual agent in a dialog mode.

12. The method of claim 1, wherein the negotiation further comprises automatically negotiating an access price to restricted information which may contain information for the response.

13. A computing device for providing a response to a user query, the computing device comprising:

a processor;

means for controlling the processor to receive the user query;

means for controlling the processor to extract key data from the user query;

means for controlling the processor to submit the key data to a data base search engine to execute a search to retrieve a top n pages from the data base, wherein “

n”

is an integer;

means for controlling the processor to preprocess pages in the top n pages if a restriction exists to access the top n pages, by negotiating the restriction by automatically providing user login and password information, overcome the restriction;

means for controlling the processor, prior to responding to the user query, to process of the top n pages through a natural language dialog engine to generate text for the response;

means for controlling the processor to provide the response comprising an audible response and a text-based response based on the text from processing the top n pages, wherein the response includes a link to more information related to the response;

means for, after providing the response and without further user input, controlling the processor to automatically expand the search based on the user query by continuing to find related information using a machine learning process; and

forwarding, for display to the user, an option to view the related information separate from the provided response.

14. A computing device for providing a response to a query, the computing device comprising:

a processor;

a first module controlling the processor to receive a user query;

a second module controlling the processor to extract key data from the user query;

a third module controlling the processor to submit the key data to a data base search engine to execute a search to retrieve a top n pages from the data base, wherein “

n”

is an integer;

a fourth module controlling the processor to preprocess pages in the top n pages if a restriction exists to access the top n pages, by negotiating the restriction by automatically providing user login and password information, overcome the restriction;

a fifth module controlling the processor, prior to responding to the user query, to process of the top n pages through a natural language dialog engine to generate text for a response;

a sixth module controlling the processor to provide a response comprising an audible response and a text-based response based on the text from processing the top n pages, wherein the response includes a link to more information related to the response;

a seventh module controlling the processor, after providing the response and without further user input to automatically expand the search based on the user query by continuing to find related information using a machine learning process; and

forwarding, for display to the user, an option to view the related information separate from the provided response.

15. A non-transitory computer readable medium storing instructions for controlling a computing device to perform the steps:

receiving a user query;

extracting key data from the user query;

submitting the key data to a data base search engine to execute a search to retrieve a top n pages from the data base, wherein “

n”

is an integer;

preprocessing pages in the top n pages if a restriction exists to access the top n pages, by negotiating the restriction by automatically providing user login and password information, overcome the restriction;

prior to responding to the user query, processing of the top n pages through a natural language dialog engine to generate text for a response;

providing the response comprising an audible response and a text-based response based on the text from processing the top n pages, wherein the response includes a link to more information related to the response; and

after providing the response and without further user input, automatically expanding the search based on the user query by continuing to find related information using a machine learning process; and

forwarding, for display to the user, an option to view the related information separate from the provided response.